In [2]:
!{sys.executable} --version

Python 3.7.9

import necessary libraries¶

In [3]:
import pandas as pd
import numpy as np
import plotly.express as px
import plotly
import plotly.graph_objs as go
from plotly import tools
from plotly.offline import init_notebook_mode, plot, iplot

Load Data¶

This data will be renewed day by day¶

In [4]:
data = pd.read_csv('https://raw.githubusercontent.com/datasets/covid-19/master/data/countries-aggregated.csv')
data.head()
Out[4]:
Date Country Confirmed Recovered Deaths
0 2020-01-22 Afghanistan 0 0 0
1 2020-01-23 Afghanistan 0 0 0
2 2020-01-24 Afghanistan 0 0 0
3 2020-01-25 Afghanistan 0 0 0
4 2020-01-26 Afghanistan 0 0 0
In [5]:
data.tail(10)
Out[5]:
Date Country Confirmed Recovered Deaths
82358 2021-03-16 Zimbabwe 36535 34124 1507
82359 2021-03-17 Zimbabwe 36552 34136 1508
82360 2021-03-18 Zimbabwe 36611 34226 1509
82361 2021-03-19 Zimbabwe 36652 34249 1510
82362 2021-03-20 Zimbabwe 36662 34257 1510
82363 2021-03-21 Zimbabwe 36665 34269 1512
82364 2021-03-22 Zimbabwe 36684 34315 1514
82365 2021-03-23 Zimbabwe 36717 34447 1516
82366 2021-03-24 Zimbabwe 36749 34476 1516
82367 2021-03-25 Zimbabwe 36778 34555 1518
In [6]:
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 82368 entries, 0 to 82367
Data columns (total 5 columns):
 #   Column     Non-Null Count  Dtype 
---  ------     --------------  ----- 
 0   Date       82368 non-null  object
 1   Country    82368 non-null  object
 2   Confirmed  82368 non-null  int64 
 3   Recovered  82368 non-null  int64 
 4   Deaths     82368 non-null  int64 
dtypes: int64(3), object(2)
memory usage: 3.1+ MB
In [7]:
data.describe()
Out[7]:
Confirmed Recovered Deaths
count 8.236800e+04 8.236800e+04 82368.000000
mean 2.015106e+05 1.184990e+05 5096.977455
std 1.194945e+06 6.261371e+05 24804.586512
min 0.000000e+00 0.000000e+00 0.000000
25% 1.320000e+02 2.600000e+01 1.000000
50% 4.236500e+03 1.976000e+03 74.000000
75% 5.690275e+04 3.000775e+04 976.250000
max 3.007928e+07 1.126464e+07 546822.000000

Visualiize the data with plotly¶

In [8]:
fig = px.choropleth(data,locations='Country',locationmode='country names',color='Confirmed',animation_frame='Date')
fig.update_layout(title='Choropleth Map of Confirmed Cases -till today',template="plotly_dark")
fig.show()
In [9]:
fig = px.choropleth(data,locations='Country',locationmode='country names',color='Confirmed',animation_frame='Date',scope='africa')
fig.update_layout(title='Choropleth Map of Confirmed Cases - Africa till today',template="plotly_dark")
fig.show()

Spread over Time¶

In [10]:
fig = px.scatter_geo(data,locations='Country',locationmode='country names',color='Confirmed',size='Confirmed',hover_name="Country",animation_frame='Date',title='Spread over Time')
fig.update(layout_coloraxis_showscale=True,layout_template="plotly_dark")
fig.show()
In [11]:
fig = px.choropleth(data,locations='Country',locationmode='country names',color='Recovered',animation_frame='Date')
fig.update_layout(title='Choropleth Map of Recovered Cases -till today',template="plotly_dark")
fig.show()
In [12]:
fig = px.scatter_geo(data,locations='Country',locationmode='country names',color='Recovered',size='Recovered',hover_name="Country",animation_frame='Date',title='Recovery over Time')
fig.update(layout_coloraxis_showscale=True,layout_template="plotly_dark")
fig.show()
In [13]:
fig = px.choropleth(data,locations='Country',locationmode='country names',color='Deaths',animation_frame='Date')
fig.update_layout(title='Choropleth Map of Deaths -till today',template="plotly_dark")
fig.show()
In [14]:
fig = px.scatter_geo(data,locations='Country',locationmode='country names',color='Deaths',size='Deaths',hover_name="Country",animation_frame='Date',title='Deaths over Time')
fig.update(layout_coloraxis_showscale=True,layout_template="plotly_dark")
fig.show()

extract latitudes & longtidues of locations¶

In [15]:
import geopy
from geopy.geocoders import Nominatim
In [16]:
geolocator=Nominatim(user_agent="app")
In [17]:
location = geolocator.geocode("Egypt")
print(location.latitude, location.longitude)

26.2540493 29.2675469
In [18]:
# copy the data to make changing
df = data.copy()
In [19]:
df
Out[19]:
Date Country Confirmed Recovered Deaths
0 2020-01-22 Afghanistan 0 0 0
1 2020-01-23 Afghanistan 0 0 0
2 2020-01-24 Afghanistan 0 0 0
3 2020-01-25 Afghanistan 0 0 0
4 2020-01-26 Afghanistan 0 0 0
... ... ... ... ... ...
82363 2021-03-21 Zimbabwe 36665 34269 1512
82364 2021-03-22 Zimbabwe 36684 34315 1514
82365 2021-03-23 Zimbabwe 36717 34447 1516
82366 2021-03-24 Zimbabwe 36749 34476 1516
82367 2021-03-25 Zimbabwe 36778 34555 1518

82368 rows × 5 columns

In [20]:
df[df['Country']=='Egypt'].tail(10)
Out[20]:
Date Country Confirmed Recovered Deaths
23156 2021-03-16 Egypt 192195 148089 11384
23157 2021-03-17 Egypt 192840 148424 11431
23158 2021-03-18 Egypt 193482 148823 11472
23159 2021-03-19 Egypt 194127 149256 11512
23160 2021-03-20 Egypt 194771 149489 11557
23161 2021-03-21 Egypt 195418 149934 11598
23162 2021-03-22 Egypt 196061 150424 11637
23163 2021-03-23 Egypt 196709 150924 11680
23164 2021-03-24 Egypt 197350 151444 11720
23165 2021-03-25 Egypt 198011 151765 11768
In [21]:
# Know the maximum value 
df2=df.groupby(['Country'])[['Confirmed','Recovered','Deaths']].max().reset_index()
In [22]:
df2
Out[22]:
Country Confirmed Recovered Deaths
0 Afghanistan 56226 49937 2467
1 Albania 122767 87760 2184
2 Algeria 116543 81065 3071
3 Andorra 11687 11111 114
4 Angola 21914 20190 532
... ... ... ... ...
187 Vietnam 2579 2265 35
188 West Bank and Gaza 232038 205289 2521
189 Yemen 3816 1580 810
190 Zambia 87318 83895 1191
191 Zimbabwe 36778 34555 1518

192 rows × 4 columns

In [23]:
df2[df2['Country']=='Egypt']
Out[23]:
Country Confirmed Recovered Deaths
53 Egypt 198011 151765 11768
In [24]:
lat_lon=[]
geolocator=Nominatim(user_agent="app")
for location in df2['Country']:
    location = geolocator.geocode(location)
    if location is None:
        lat_lon.append(np.nan)
    else:    
        geo=(location.latitude,location.longitude)
        lat_lon.append(geo)
In [25]:
lat_lon
Out[25]:
[(33.7680065, 66.2385139),
 (41.000028, 19.9999619),
 (28.0000272, 2.9999825),
 (42.5407167, 1.5732033),
 (-11.8775768, 17.5691241),
 (17.2234721, -61.9554608),
 (-34.9964963, -64.9672817),
 (40.7696272, 44.6736646),
 (-24.7761086, 134.755),
 (47.69641095, 14.754807384371395),
 (40.3936294, 47.7872508),
 (24.7736546, -78.0000547),
 (26.1551249, 50.5344606),
 (24.4768783, 90.2932426),
 (13.1500331, -59.5250305),
 (53.4250605, 27.6971358),
 (50.6402809, 4.6667145),
 (16.8259793, -88.7600927),
 (9.2231105, 2.31006719638123),
 (27.549511, 90.5119273),
 (-17.0568696, -64.9912286),
 (44.3053476, 17.5961467),
 (-23.1681782, 24.5928742),
 (-10.3333333, -53.2),
 (4.4137155, 114.5653908),
 (42.72572155, 25.336199594318522),
 (12.0753083, -1.6880314),
 (17.1750495, 95.9999652),
 (-3.3634357, 29.8870575),
 (16.0000552, -24.0083947),
 (13.5066394, 104.869423),
 (4.6125522, 13.1535811),
 (61.0666922, -107.991707),
 (7.0323598, 19.9981227),
 (15.6134137, 19.0156172),
 (-31.7613365, -71.3187697),
 (35.000074, 104.999927),
 (2.8894434, -73.783892),
 (-12.2045176, 44.2832964),
 (-0.7179165000000001, 16.018048574081842),
 (-2.9814344, 23.8222636),
 (9.5773243, -83.82371114343024),
 (7.9897371, -5.5679458),
 (45.5643442, 17.0118954),
 (23.0131338, -80.8328748),
 (34.9823018, 33.1451285),
 (49.8167003, 15.4749544),
 (55.670249, 10.3333283),
 (53.8953584, 27.5554078),
 (11.85677545, 42.757784519943655),
 (19.28131815, -70.035906834967),
 (19.28131815, -70.035906834967),
 (-1.3397668, -79.3666965),
 (26.2540493, 29.2675469),
 (13.8000382, -88.9140683),
 (1.613172, 10.5170357),
 (15.9500319, 37.9999668),
 (58.7523778, 25.3319078),
 (-26.5624806, 31.3991317),
 (10.2116702, 38.6521203),
 (-18.1239696, 179.0122737),
 (63.2467777, 25.9209164),
 (46.603354, 1.8883335),
 (-0.8999695, 11.6899699),
 (13.44294275, -16.118732162564726),
 (32.3293809, -83.1137366),
 (51.0834196, 10.4234469),
 (7.8573710000000005, -1.0840975468820433),
 (38.9953683, 21.9877132),
 (12.1360374, -61.6904045),
 (15.6356088, -89.8988087),
 (10.7226226, -10.7083587),
 (11.6688305, -15.535471371611191),
 (4.8417097, -58.6416891),
 (19.1399952, -72.3570972),
 (38.9247244, -77.06572732690151),
 (15.2572432, -86.0755145),
 (47.16115805, 19.135174733081314),
 (64.9841821, -18.1059013),
 (22.3511148, 78.6677428),
 (-2.4833826, 117.8902853),
 (32.6475314, 54.5643516),
 (33.0955793, 44.1749775),
 (52.865196, -7.9794599),
 (31.5313113, 34.8667654),
 (42.6384261, 12.674297),
 (18.1850507, -77.3947693),
 (36.5748441, 139.2394179),
 (31.1667049, 36.941628),
 (47.2286086, 65.2093197),
 (-0.1667169, 37.48603689110992),
 (36.638392, 127.6961188),
 (42.5653218, 20.913641374540397),
 (29.2733964, 47.4979476),
 (41.5089324, 74.724091),
 (20.0171109, 103.378253),
 (56.8406494, 24.7537645),
 (33.8750629, 35.843409),
 (-29.6039267, 28.3350193),
 (5.7499721, -9.3658524),
 (26.4215275, 17.30331995251014),
 (47.1594125, 9.546911556940856),
 (55.3500003, 23.7499997),
 (49.8158683, 6.1296751),
 (52.4387696, 4.8185293),
 (-18.9249604, 46.4416422),
 (-13.2687204, 33.9301963),
 (4.5693754, 102.2656823),
 (4.7064352, 73.3287853),
 (16.3700359, -2.2900239),
 (35.9446731, 14.383630615858262),
 (8.9995549, 168.0002575),
 (20.2540382, -9.2399263),
 (-20.2759451, 57.5703566),
 (22.5000485, -100.0000375),
 (8.6065, 152.00846930625),
 (47.2879608, 28.5670941),
 (43.73844905, 7.424224092532953),
 (46.8250388, 103.8499736),
 (42.9868853, 19.5180992),
 (31.1728205, -7.3362482),
 (-19.302233, 34.9144977),
 (-23.2335499, 17.3231107),
 (28.1083929, 84.0917139),
 (52.5001698, 5.7480821),
 (-41.5000831, 172.8344077),
 (12.6090157, -85.2936911),
 (17.7356214, 9.3238432),
 (9.6000359, 7.9999721),
 (41.6171214, 21.7168387),
 (60.5000209, 9.0999715),
 (21.0000287, 57.0036901),
 (30.3308401, 71.247499),
 (8.559559, -81.1308434),
 (-5.6816069, 144.2489081),
 (-23.3165935, -58.1693445),
 (-6.8699697, -75.0458515),
 (12.7503486, 122.7312101),
 (52.215933, 19.134422),
 (39.4332242, -8.567392135367742),
 (25.3336984, 51.2295295),
 (45.9852129, 24.6859225),
 (64.6863136, 97.7453061),
 (-1.9646631, 30.0644358),
 (17.250512, -62.6725973),
 (13.8250489, -60.975036),
 (12.90447, -61.2765569),
 (-13.7693895, -172.1200508),
 (43.9458623, 12.458306),
 (0.8875498, 6.9648718),
 (25.6242618, 42.3528328),
 (14.46517725, -14.765340959100413),
 (44.1534121, 20.55144),
 (-4.6574977, 55.4540146),
 (8.6400349, -11.8400269),
 (1.357107, 103.8194992),
 (48.6726975, 19.63679421037233),
 (46.149034549999996, 14.626325753340627),
 (-8.7053941, 159.1070693851845),
 (8.3676771, 49.083416),
 (-28.579397200000002, 24.086794125366062),
 (7.8699431, 29.6667897),
 (39.3260685, -4.8379791),
 (7.5554942, 80.7137847),
 (14.5844444, 29.4917691),
 (4.1413025, -56.0771187),
 (59.6749712, 14.5208584),
 (46.813331250000005, 8.444947437939408),
 (34.6401861, 39.0494106),
 (23.9739374, 120.9820179),
 (38.6281733, 70.8156541),
 (-6.5247123, 35.7878438),
 (14.8971921, 100.83273),
 (-8.5151979, 125.8375756),
 (8.7800265, 1.0199765),
 (10.8677845, -60.9821067),
 (33.994952999999995, 9.367097748325554),
 (38.9597594, 34.9249653),
 (39.7837304, -100.4458825),
 (1.3769751000000001, 32.72391099113675),
 (49.4871968, 31.2718321),
 (24.0002488, 53.9994829),
 (54.7023545, -3.2765753),
 (-32.8755548, -56.0201525),
 (41.32373, 63.9528098),
 (-16.5255069, 168.1069154),
 (8.0018709, -66.1109318),
 (13.2904027, 108.4265113),
 (31.9049661, 35.2023413),
 (16.3471243, 47.8915271),
 (-14.5189121, 27.5589884),
 (-19.01688, 29.35365015971339)]
In [26]:
df2['geo_loc']=lat_lon
In [27]:
lat,lon=zip(*np.array(df2['geo_loc']))
In [28]:
df2['lat']=lat
df2['lon']=lon
In [29]:
df2
Out[29]:
Country Confirmed Recovered Deaths geo_loc lat lon
0 Afghanistan 56226 49937 2467 (33.7680065, 66.2385139) 33.768006 66.238514
1 Albania 122767 87760 2184 (41.000028, 19.9999619) 41.000028 19.999962
2 Algeria 116543 81065 3071 (28.0000272, 2.9999825) 28.000027 2.999983
3 Andorra 11687 11111 114 (42.5407167, 1.5732033) 42.540717 1.573203
4 Angola 21914 20190 532 (-11.8775768, 17.5691241) -11.877577 17.569124
... ... ... ... ... ... ... ...
187 Vietnam 2579 2265 35 (13.2904027, 108.4265113) 13.290403 108.426511
188 West Bank and Gaza 232038 205289 2521 (31.9049661, 35.2023413) 31.904966 35.202341
189 Yemen 3816 1580 810 (16.3471243, 47.8915271) 16.347124 47.891527
190 Zambia 87318 83895 1191 (-14.5189121, 27.5589884) -14.518912 27.558988
191 Zimbabwe 36778 34555 1518 (-19.01688, 29.35365015971339) -19.016880 29.353650

192 rows × 7 columns

In [30]:
df2.drop(['geo_loc'],axis=1,inplace=True)
In [31]:
df2
Out[31]:
Country Confirmed Recovered Deaths lat lon
0 Afghanistan 56226 49937 2467 33.768006 66.238514
1 Albania 122767 87760 2184 41.000028 19.999962
2 Algeria 116543 81065 3071 28.000027 2.999983
3 Andorra 11687 11111 114 42.540717 1.573203
4 Angola 21914 20190 532 -11.877577 17.569124
... ... ... ... ... ... ...
187 Vietnam 2579 2265 35 13.290403 108.426511
188 West Bank and Gaza 232038 205289 2521 31.904966 35.202341
189 Yemen 3816 1580 810 16.347124 47.891527
190 Zambia 87318 83895 1191 -14.518912 27.558988
191 Zimbabwe 36778 34555 1518 -19.016880 29.353650

192 rows × 6 columns

In [32]:
import folium
In [33]:
folium.Map(zoom_start=2)
Out[33]:
Make this Notebook Trusted to load map: File -> Trust Notebook
In [34]:
# Create a map
m = folium.Map(location=[54, 15], tiles='openstreetmap',zoom_start=2)

# Add points to the map
for id,row in df2.iterrows():
    folium.Marker(location=[row['lat'],row['lon']], popup=row['Confirmed']).add_to(m)

# Display the map
m
Out[34]:
Make this Notebook Trusted to load map: File -> Trust Notebook
In [35]:
for id,row in df2.iterrows():
    folium.Marker(location=[row['lat'],row['lon']], popup=row['Recovered']).add_to(m)

# Display the map
m
Out[35]:
Make this Notebook Trusted to load map: File -> Trust Notebook
In [36]:
m = folium.Map(location=[54, 15], tiles='openstreetmap', zoom_start=2)

# Add points to the map
for idx, row in df2.iterrows():
    folium.Marker([row['lat'], row['lon']], popup=row['Deaths']).add_to(m)

# Display the map
m
Out[36]:
Make this Notebook Trusted to load map: File -> Trust Notebook
In [37]:
m = folium.Map(location=[54,15], tiles='cartodbpositron', zoom_start=2)

# Add points to the map
from folium.plugins import MarkerCluster
mc = MarkerCluster()
for idx, row in df2.iterrows():
    mc.add_child(folium.Marker([row['lat'], row['lon']],popup=row['Confirmed']))
m.add_child(mc)

# Display the map
m
Out[37]:
Make this Notebook Trusted to load map: File -> Trust Notebook
In [38]:
from folium.plugins import HeatMap
In [39]:
df2
Out[39]:
Country Confirmed Recovered Deaths lat lon
0 Afghanistan 56226 49937 2467 33.768006 66.238514
1 Albania 122767 87760 2184 41.000028 19.999962
2 Algeria 116543 81065 3071 28.000027 2.999983
3 Andorra 11687 11111 114 42.540717 1.573203
4 Angola 21914 20190 532 -11.877577 17.569124
... ... ... ... ... ... ...
187 Vietnam 2579 2265 35 13.290403 108.426511
188 West Bank and Gaza 232038 205289 2521 31.904966 35.202341
189 Yemen 3816 1580 810 16.347124 47.891527
190 Zambia 87318 83895 1191 -14.518912 27.558988
191 Zimbabwe 36778 34555 1518 -19.016880 29.353650

192 rows × 6 columns

In [40]:
# Create map with overall cases registered
m = folium.Map(location=[54,15], zoom_start=2)
HeatMap(data=df2[['lat', 'lon','Confirmed']], radius=15).add_to(m)

# Show the map
m
Out[40]:
Make this Notebook Trusted to load map: File -> Trust Notebook
In [ ]: